• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.

• Journal of agricultural medicine and community health
• /
• v.25 no.1
• /
• pp.51-63
• /
• 2000

Ten Dongs were selected according to the systematic cluster sampling in Koryong Gun, and the survey was conducted on 571 women in the age between 30-69 years. The first survey was performed for 6 days between August 27 to September 1, 1999 with the investigation rate of 60.3%, and the second survey was performed in November with the investigation rate of 91.8%. The contents of survey included demographic characteristics, health behaviors, dyspepsia symptom score, sleeping induction time and the degree of sleep satisfaction, and degree of stress in the subjects. The dyspepsia symptom score was in the average 13.4 points out of a total 44 points and was the highest in the 50-59 year-old age group with 13.9 points. The sleep induction time was in the average of 35 minutes and was the highest in the 50-59 year-old age group with 40.9 minutes; the degree of sleep satisfaction was in the average of 7.9 points and was the lowest in the 50-59 year-old age group with 7.5 points. The stress score was in the average of 18.3 points and was highest in those subjects in their 40's and 50's with 18.7 points. When the correlation among the stress score, the degree of sleep satisfaction and dyspepsia symptom score was analyzed, the results showed that he stress score and the degree of sleep satisfaction showed a significant negative correlation and that the stress score and dyspepsia symptom score showed a significant positive correlation. Also, a significant negative correlation was found between the degree of sleep satisfaction and dyspepsia symptom score. According to each age group, a significant correlation was revealed among the stress score, dyspepsia symptom score and the degree of sleep satisfaction in those subjects over 40 years of age compared to those subjects who were younger than 40 years of age. As for educational level, the correlation among the stress score, the degree of sleep satisfaction and dyspepsia symptom score was higher in those subjects with less than middle school education compared to those subjects with more than high school education. When those factors that effects on the dyspepsia symptom score were analyzed with multiple regression, the results showed that the level of stress and chronic diseases were selected as significant variables. When those factors that affected on the degree of sleep satisfaction were analyzed, the sleep induction time and presence of chronic diseases and stress were selected as significant variables. Those women in their 50's who live in rural areas showed the highest level of stress, lowest the degree of sleep satisfaction, and highest level of dyspepsia, indicating that they need stress management. Also, since stress was showed to be a significant variable effecting on dyspepsia or the degree of sleep satisfaction, it is concluded that health promotion is possible through stress management. More studies are needed in the future on coping resources that would strengthen coping against stress, and by conducting studies on stress and related factors on community people, the measures of mental health promotion need to be developed.

• Radiation Oncology Journal
• /
• v.19 no.3
• /
• pp.216-223
• /
• 2001

Purpose : We evaluated retrospectively the outcomes of inoperable squamous cell lung cancer patients treated with radiotherapy to find out prognostic factors affecting survival. Materials and methods : Four hundred and eleven patients diagnosed as squamous cell lung cancer between November 1988 and December 1997 were the basis of this analyses. The planned dose to the gross tumor volume was ranged from 30 to 70.2 Gy. Chemotherapy was combined in 72 patients $(17.5\%)$ with the variable schedule and drug combination regimens. Follow-up period ranged from 1 to 113 months with the median of 8 months and survival status was identified in 381 patients $(92.7\%)$. Overall survival rate was calculated using the Kaplan-Meier method. Results : Age ranged from 23 years to 83 years with the median 63 years. The male to female ratio was about 16:1. For all 411 patients, the median overall survival was 8 months and the 1-year survival rate (YSR), 2-YSR, and 5-YSR were $35.6\%,\;12.6\%,\;and\;3.7\%$, respectively. The median and 5-YSR were 29 months and $33.3\%$ for Stage IA, 13 months and $6.3\%$ for Stage IIIA, and 9 months and $3.4\%$ for Stage IIIB, respectively(p=0.00). The median survival by treatment aim was 11 months in radical intent group and 5 months in palliative, respectively (p=0.00). Of 344 patients treated with radical intent, median survival of patients (N=247) who received planned radiotherapy completely was 12 months while that of patients (N=97) who did not was 5 months (p=0.0006). In the analyses of the various prognostic factors affecting to the survival outcomes in 247 patients who completed the planned radiotherapy, tumor location, supraclavicular LAP, SVC syndrome, pleural effusion, total lung atelectasis and hoarseness were statistically significant prognostic factors both in the univariate and multivariate analyses while the addition of chemotherapy was statistically significant only in multivariate analyses. The acute radiation esophagitis requiring analgesics was appeared in 49 patients $(11.9\%)$ and severe radiation esophagitis requiring hospitalization was shown in 2 patients $(0.5\%)$. The radiation pneumonitis requiring steroid medication was shown in 62 patients $(15.1\%)$ and severe pneumonitis requiring hospitalization was occurred in 2 patients $(0.5\%)$. During follow-up, 114 patients $(27.7\%)$ had progression of local disease with 10 months of median time to recur (range : $1\~87\;months$) and 49 patients $(11.9\%)$ had distant failure with 7 months of median value (range : $1\~52\;months$). Second malignancy before or after the diagnosis of lung cancer was appeared in 11 patients Conclusion : The conventional radiotherapy in the patients with locally advanced squamous cell lung cancer has given small survival advantage over supportive care and it is very important to select the patient group who can obtain the maximal benefit and to select the radiotherapy technique that would not compromise the life quality in these patients.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.63-83
• /
• 2019

Investors prefer to look for trading points based on the graph shown in the chart rather than complex analysis, such as corporate intrinsic value analysis and technical auxiliary index analysis. However, the pattern analysis technique is difficult and computerized less than the needs of users. In recent years, there have been many cases of studying stock price patterns using various machine learning techniques including neural networks in the field of artificial intelligence(AI). In particular, the development of IT technology has made it easier to analyze a huge number of chart data to find patterns that can predict stock prices. Although short-term forecasting power of prices has increased in terms of performance so far, long-term forecasting power is limited and is used in short-term trading rather than long-term investment. Other studies have focused on mechanically and accurately identifying patterns that were not recognized by past technology, but it can be vulnerable in practical areas because it is a separate matter whether the patterns found are suitable for trading. When they find a meaningful pattern, they find a point that matches the pattern. They then measure their performance after n days, assuming that they have bought at that point in time. Since this approach is to calculate virtual revenues, there can be many disparities with reality. The existing research method tries to find a pattern with stock price prediction power, but this study proposes to define the patterns first and to trade when the pattern with high success probability appears. The M & W wave pattern published by Merrill(1980) is simple because we can distinguish it by five turning points. Despite the report that some patterns have price predictability, there were no performance reports used in the actual market. The simplicity of a pattern consisting of five turning points has the advantage of reducing the cost of increasing pattern recognition accuracy. In this study, 16 patterns of up conversion and 16 patterns of down conversion are reclassified into ten groups so that they can be easily implemented by the system. Only one pattern with high success rate per group is selected for trading. Patterns that had a high probability of success in the past are likely to succeed in the future. So we trade when such a pattern occurs. It is a real situation because it is measured assuming that both the buy and sell have been executed. We tested three ways to calculate the turning point. The first method, the minimum change rate zig-zag method, removes price movements below a certain percentage and calculates the vertex. In the second method, high-low line zig-zag, the high price that meets the n-day high price line is calculated at the peak price, and the low price that meets the n-day low price line is calculated at the valley price. In the third method, the swing wave method, the high price in the center higher than n high prices on the left and right is calculated as the peak price. If the central low price is lower than the n low price on the left and right, it is calculated as valley price. The swing wave method was superior to the other methods in the test results. It is interpreted that the transaction after checking the completion of the pattern is more effective than the transaction in the unfinished state of the pattern. Genetic algorithms(GA) were the most suitable solution, although it was virtually impossible to find patterns with high success rates because the number of cases was too large in this simulation. We also performed the simulation using the Walk-forward Analysis(WFA) method, which tests the test section and the application section separately. So we were able to respond appropriately to market changes. In this study, we optimize the stock portfolio because there is a risk of over-optimized if we implement the variable optimality for each individual stock. Therefore, we selected the number of constituent stocks as 20 to increase the effect of diversified investment while avoiding optimization. We tested the KOSPI market by dividing it into six categories. In the results, the portfolio of small cap stock was the most successful and the high vol stock portfolio was the second best. This shows that patterns need to have some price volatility in order for patterns to be shaped, but volatility is not the best.

• Korea Journal of Hospital Management
• /
• v.10 no.1
• /
• pp.93-114
• /
• 2005

The prenatal care is the preventive medical service to help the pregnant mother deliver the healthy baby. It's regular examines give some chances to check-up the healthy conditions. This thesis concentrates on the CRM system to support an effective prenatal care system and prove the effectiveness of it. As CRM is the adapted management related to the customer's own information, it is important to develop the CRM model classified by the patients characteristics. A general hospital in Busan operated the CRM system to carry out the effective prenatal care and there is an analysis to ensure the effectiveness of CRM system for the pregnant women in our maternity ward. The results can be summarized as follows: 1) According to the comparisons with the CRM system, we can conclude the system is desirable. (1) Maternal Age : In the age distribution, the prenatal visit frequency, triple marker freqency, oral GTT and targeted ultrasonography in the experimental group in 30 to 34 years old is higher on the whole. For over 35 years old group, the higher frequency comes out in the oral GTT and targeted ultrasonography and for 25 to 29 years old group the different figure shows just in the targeted ultrasonography. (2) Area of residence: There is a clear difference in all the items in Busan and near area but no sign of difference in prenatal visits and oral GTT in other residencial area. Especially in the targeted ultrasonography the higher figure shows in the experimental group located in the both areas. The targeted ultrasonography is known as the specific examination which should be examined by the specialists, on the contrary the other examinations can be operated in the small clinic. So the public information and seminars related with ultrasonography increases the check-up frequency. The clinic requests some ultrasonographical examinations to the specialists in general hospital. (3) Parity: The clear difference shows that the CRM system causes the prenatal visit frequency to become higher in experimental group. The figure is 9.7 times and 8.6 times each. This is opposite that the past study said multiparity reduced the average prenatal visits. But the result of CRM is considered as the method to help the multiparity understand the importance of the prenatal care. (4) Obstetrical history: In the experimental group of the spontaneous delivery group, the figure is higher in the prenatal visit frequency, triple marker, oral GTT and targeted ultrasonography but the Caesarean section delivery group has higher figure in targeted ultrasonography. (5) In the first check-up, the rate of targeted ultrasonography in under 16 week pregnancy, in the 16 week pregnancy to 32 week pregnancy and the over 32 week pregnancy in the experimental group is upper than the compared one. For the oral GTT, there is a difference in under 16 week pregnancy but no difference in prenatal visits and triple marker. 2) The analysis of characteristics of prenatal care through the decision tree resulted in the fact that the most important variable is the residential area. After the delivery frequency is following, the obstetrical history and maternal age are in order. It is the same result in the triple marker and oral GTT. Consequently it is the same order of important variables in CRM system. The effectiveness of CRM system is proved in this study. The CRM system is a marketing method to control and lead the customers through the segmentation of customer data. It increases the new customer aquisition, maintenance of loyal customers, augmentation of customers value, activation of potential customers and creation of life time customers. So eventually it can enlarge the customers value. The medical institution should make efforts to establish the data base enforced by the customer's information on the underlying ordinary data system to carry out the CRM system effectively. In addition, it should develop the a variety of marketing strategy in order to set up one to one marketing satisfying the needs of individual patients.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6B
• /
• pp.565-575
• /
• 2011

The purpose of this study was to quantitatively evaluate the expression of both multi-metric qualitative habitat evaluation index (QHEI) and biological integrity index (IBI) for artificial structures eco-artificial fish reef (EAFR) for fishes asylum and habitat. Especially, both experimental evaluation and biological verification were performed in Water and Environmental Center's outdoor test-bed of Korea Institute of Construction Technology located in Andong-city, Gyeongsangbuk-do. The experimental conditions reflecting the situation of domestic river include the flow rate (e.g., $0.0{\sim}1.5m\;s^{-1}$), the width (e.g., 1.0~3.0 m), the depth (e.g., 0.05~0.70 m), and variable bed materials. Both QHEI and IBI were monitored for 8 months from May to December 2010. Whereas QHEI values were highest at experimental points of the E~F with an average of 83.1, those were lowest at B~C with an average of 78.1. However, QHEI values inside EAFR were more than 98.9, regardelss of space and time, and indicated more than the highest good of the state (Good) in the habitat. Overally, IBI values showed similar trend with QHEI, but were 44.2 in the winter dry season, compared to 32.8 of QHEI values. IBI values Also, IBI values inside EAFR were greater than those at the experimental channel by 5.7 to 11.4% and 18.7 to 34.8% in flow and stagnant conditions, respectively, indicating that EAFR can secure asylum and habitat for fish during the dry season. For comprehensive aquatic ecosystem assessment, the experimental channel showed generally fair conditions (Fair~Good), whereas EAFR showed good conditions (Good), suggesting that EAFR can be applied to aquatic ecosystem restoration and improvement.

• Korean Journal of Environment and Ecology
• /
• v.31 no.4
• /
• pp.381-396
• /
• 2017

Understanding species distribution plays an important role in conservation as well as evolutionary biology. In this study, we applied a species distribution model to predict hotspot areas and habitat characteristics for endangered herpetofauna species in South Korea: the Korean Crevice Salamander (Karsenia koreana), Suweon-tree frog (Hyla suweonensis), Gold-spotted pond frog (Pelophylax chosenicus), Narrow-mouthed toad (Kaloula borealis), Korean ratsnake (Elaphe schrenckii), Mongolian racerunner (Eremias argus), Reeve's turtle (Mauremys reevesii) and Soft-shelled turtle (Pelodiscus sinensis). The Kori salamander (Hynobius yangi) and Black-headed snake (Sibynophis chinensis) were excluded from the analysis due to insufficient sample size. The results showed that the altitude was the most important environmental variable for their distribution, and the altitude at which these species were distributed correlated with the climate of that region. The predicted distribution area derived from the species distribution modelling adequately reflected the observation site used in this study as well as those reported in preceding studies. The average AUC value of the eigh species was relatively high ($0.845{\pm}0.08$), while the average omission rate value was relatively low ($0.087{\pm}0.01$). Therefore, the species overlaying model created for the endangered species is considered successful. When merging the distribution models, it was shown that five species shared their habitats in the coastal areas of Gyeonggi-do and Chungcheongnam-do, which are the western regions of the Korean Peninsula. Therefore, we suggest that protection should be a high priority in these area, and our overall results may serve as essential and fundamental data for the conservation of endangered amphibian and reptiles in Korea.

• Journal of Intelligence and Information Systems
• /
• v.23 no.1
• /
• pp.127-141
• /
• 2017

Advances in Internet technologies and the proliferation of mobile devices enabled consumers to approach a wide range of goods and services, while causing an adverse effect that they have hard time reaching their congenial items even if they devote much time to searching for them. Accordingly, businesses are using the recommender systems to provide tools for consumers to find the desired items more easily. Association Rule Mining (ARM) technology is advantageous to recommender systems in that ARM provides intuitive form of a rule with interestingness measures (support, confidence, and lift) describing the relationship between items. Given an item, its relevant items can be distinguished with the help of the measures that show the strength of relationship between items. Based on the strength, the most pertinent items can be chosen among other items and exposed to a given item's web page. However, the diversity of the measures may confuse which items are more recommendable. Given two rules, for example, one rule's support and confidence may not be concurrently superior to the other rule's. Such discrepancy of the measures in distinguishing one rule's superiority from other rules may cause difficulty in selecting proper items for recommendation. In addition, in an online environment where a web page or mobile screen can provide a limited number of recommendations that attract consumer interest, the prudent selection of items to be included in the list of recommendations is very important. The exposure of items of little interest may lead consumers to ignore the recommendations. Then, such consumers will possibly not pay attention to other forms of marketing activities. Therefore, the measures should be aligned with the probability of consumer's acceptance of recommendations. For this reason, this study proposes a model-based approach to combine those measures into one unified measure that can consistently determine the ranking of recommended items. A regression model was designed to describe how well the measures (independent variables; i.e., support, confidence, and lift) explain consumer's acceptance of recommendations (dependent variables, hit rate of recommended items). The model is intuitive to understand and easy to use in that the equation consists of the commonly used measures for ARM and can be used in the estimation of hit rates. The experiment using transaction data from one of the Korea's largest online shopping malls was conducted to show that the proposed model can improve the hit rates of recommendations. From the top of the list to 13th place, recommended items in the higher rakings from the proposed model show the higher hit rates than those from the competitive model's. The result shows that the proposed model's performance is superior to the competitive model's in online recommendation environment. In a web page, consumers are provided around ten recommendations with which the proposed model outperforms. Moreover, a mobile device cannot expose many items simultaneously due to its limited screen size. Therefore, the result shows that the newly devised recommendation technique is suitable for the mobile recommender systems. While this study has been conducted to cover the cross-selling in online shopping malls that handle merchandise, the proposed method can be expected to be applied in various situations under which association rules apply. For example, this model can be applied to medical diagnostic systems that predict candidate diseases from a patient's symptoms. To increase the efficiency of the model, additional variables will need to be considered for the elaboration of the model in future studies. For example, price can be a good candidate for an explanatory variable because it has a major impact on consumer purchase decisions. If the prices of recommended items are much higher than the items in which a consumer is interested, the consumer may hesitate to accept the recommendations.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.13 no.2
• /
• pp.177-192
• /
• 2018

The mission of the university is to grow young people who will be responsible for the next generation nation to mature society. In particular, the role of universities in the 4th Industrial Revolution era is to foster creative talents. Therefore, innovative changes are required for existing infusion education and employment-oriented college education contents and teaching methodology. In the high youth unemployment rate, entrepreneurship education is spreading to universities to innovate existing organizations and create new jobs. Until now, however, the effects of university entrepreneurship education have been studied mainly in the field of start-up. Therefore, it is very difficult to study various effects on entrepreneurship education. In this study, empirical analysis of the effect of entrepreneurship training on career preparation behaviors of university students who are about to enter the society is verified. The sample of this study was surveyed from August, 2016, and the questionnaire was applied to 393 university students who selected 5 universities and entrepreneurship education. As a result of the analysis, the ability of communicative communication and creative problem solving cultivated through entrepreneurship education had a positive effect on entrepreneurship and self - efficacy, Entrepreneurship and self - efficacy had a positive (+) positive effect on career preparation behavior. However, cooperative communication ability, creative problem solving ability, and effective work behavior ability by entrepreneurship education were not directly related to career preparation behavior. On the other hand, in verifying the mediating effect of entrepreneurship and self - efficacy, it proved that mediating role of positive communication between collaborative communication ability, creative problem solving ability and career preparation behavior. The implications of this study are as follows This study examines the effects of university entrepreneurship education on career preparedness behaviors.In other words, the university proved the direct effect and the mediating effect that affects positively (+) effect on career preparation behaviors by encouraging entrepreneurship and self - efficacy, rather than quantitative extension based on competency. Also, the implication of the parameters (entrepreneurship, self - efficacy) as a key variable for the effect and performance of career preparation behavior was derived.It also suggests that it is necessary to improve the creativity ability of entrepreneurship education so that it can have a direct and meaningful influence on career preparation behavior. First of all, it is urgent to develop a qualitative evaluation index for entrepreneurship education in order to measure these effects. Therefore, further study is required to verify the various implications for future entrepreneurship education, as well as the implications that entrepreneurship education is indispensable for the preparation of university students' careers.